Rajat Ghosh PRO
rghosh8
AI & ML interests
None yet
Recent Activity
updated a Space 3 days ago
rghosh8/grpo-explorer published a Space 3 days ago
rghosh8/grpo-explorer liked a dataset 24 days ago
adityasoni17/SWE-TesterOrganizations
ARC-GRPO
-
rghosh8/arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged
2B • Updated • 4 -
rghosh8/arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new
Text Generation • Updated • 11 • 1 -
rghosh8/arc-grpo-nemotron-mini-4b-instruct-rajat-seed-3407-G-4_merged
4B • Updated • 2 -
rghosh8/arc-grpo-nemotron-mini-4b-instruct-rajat-seed-3407-G-4
Text Generation • Updated • 8
GSM8k-GRPO
-
rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-42-G-16
Text Generation • Updated • 7 -
rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-42-G-16_merged
Text Generation • 7B • Updated • 13 -
rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-3407-G-16
Text Generation • Updated • 10 -
rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-3407-G-16_merged
Text Generation • 7B • Updated • 9
arc-grpo-baseline
-
rghosh8/arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-baseline
Text Generation • Updated • 9 -
rghosh8/arc-grpo-deepseek-llm-7b-chat-rajat-seed-42-G-4
Text Generation • Updated • 7 -
rghosh8/arc-grpo-deepseek-llm-7b-chat-rajat-seed-42-G-16
Text Generation • Updated • 5 -
rghosh8/arc-grpo-deepseek-llm-7b-chat-rajat-seed-3407-G-4
Text Generation • Updated • 7
Opencoder-GRPO
-
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-42-G-4-merged
2B • Updated • 6 -
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-42-G-4
Text Generation • Updated • 11 -
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-3407-G-8
Text Generation • Updated • 11 -
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-3407-G-8_merged
2B • Updated • 7
ROBOT-OpenVLA
arc-grpo-baseline
-
rghosh8/arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-baseline
Text Generation • Updated • 9 -
rghosh8/arc-grpo-deepseek-llm-7b-chat-rajat-seed-42-G-4
Text Generation • Updated • 7 -
rghosh8/arc-grpo-deepseek-llm-7b-chat-rajat-seed-42-G-16
Text Generation • Updated • 5 -
rghosh8/arc-grpo-deepseek-llm-7b-chat-rajat-seed-3407-G-4
Text Generation • Updated • 7
ARC-GRPO
-
rghosh8/arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new_merged
2B • Updated • 4 -
rghosh8/arc-grpo-deepseek-r1-distill-qwen-1.5b-rajat-seed-42-G-4-new
Text Generation • Updated • 11 • 1 -
rghosh8/arc-grpo-nemotron-mini-4b-instruct-rajat-seed-3407-G-4_merged
4B • Updated • 2 -
rghosh8/arc-grpo-nemotron-mini-4b-instruct-rajat-seed-3407-G-4
Text Generation • Updated • 8
Opencoder-GRPO
-
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-42-G-4-merged
2B • Updated • 6 -
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-42-G-4
Text Generation • Updated • 11 -
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-3407-G-8
Text Generation • Updated • 11 -
rghosh8/deepseek-r1-distill-qwen-1.5b-opencoder-educational-instruct-seed-3407-G-8_merged
2B • Updated • 7
GSM8k-GRPO
-
rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-42-G-16
Text Generation • Updated • 7 -
rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-42-G-16_merged
Text Generation • 7B • Updated • 13 -
rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-3407-G-16
Text Generation • Updated • 10 -
rghosh8/gsm8k-deepseek-llm-7b-chat-rajat-seed-3407-G-16_merged
Text Generation • 7B • Updated • 9